Title is wrong, only the distilled models from llama, qwen are on ollama, not the actual official MoE r1 model from deepseekv3.
4 bit quantized: ollama run deepseek-r1:671b
(400GB+ VRAM/Unified memory required to run this)
https://ollama.com/library/deepseek-r1/tags
8 bit quantization still being uploaded